Peformance Prediction for Coarse-Grained Locking: MCS Case

TL;DR

This paper extends stochastic performance analysis from CLH lock-based algorithms to those using MCS locks, aiding in predicting throughput of coarse-grained locking in concurrent data structures.

Contribution

It introduces an extended analysis method for MCS lock-based algorithms, building on prior CLH lock analysis, to improve throughput prediction accuracy.

Findings

Extended stochastic analysis for MCS locks

Improved throughput prediction for lock-based algorithms

Applicable to concurrent data structures like hash tables

Abstract

A standard design pattern found in many concurrent data structures, such as hash tables or ordered containers, is alternation of parallelizable sections that incur no data conflicts and critical sections that must run sequentially and are protected with locks. It was already shown that simple stochastic analysis can predict the throughput of coarse-grained lock-based algorithms using CLH lock. In this short paper, we extend this analysis to algorithms based on the popular MCS lock.